如何读取 i5、i7 CPU 上的性能计数器

发布于 2024-12-15 08:16:51 字数 365 浏览 1 评论 0 原文

现代 CPU 有相当多的性能计数器 - http://www.intel.com/content/www/us/en/architecture-and-technology/64-ia-32-architectures-software-developer-system-programming-manual-325384。 html 如何读取它们？我对缓存未命中和分支预测错误感兴趣。

原文

分享到QQ

分享到微博

如果你对这篇内容有疑问，欢迎到本站社区发帖提问参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。

发布评论

需要登录才能够评论，你可以免费注册一个本站的账号。

枫以 2024-12-22 08:16:51

看起来 PAPI 有非常干净的 API 并且工作得很好乌班图11.04。
安装后，以下应用程序将执行我想要的操作：

#include <stdio.h>
#include <stdlib.h>
#include <papi.h>

#define NUM_EVENTS 4

void matmul(const double *A, const double *B,
        double *C, int m, int n, int p)
{
    int i, j, k;
    for (i = 0; i < m; ++i)
        for (j = 0; j < p; ++j) {
            double sum = 0;
            for (k = 0; k < n; ++k)
                sum += A[i*n + k] * B[k*p + j];
            C[i*p + j] = sum;
        }
}

int main(int /* argc */, char ** /* argv[] */)
{
    const int size = 300;
    double a[size][size];
    double b[size][size];
    double c[size][size];

    int event[NUM_EVENTS] = {PAPI_TOT_INS, PAPI_TOT_CYC, PAPI_BR_MSP, PAPI_L1_DCM };
    long long values[NUM_EVENTS];

    /* Start counting events */
    if (PAPI_start_counters(event, NUM_EVENTS) != PAPI_OK) {
        fprintf(stderr, "PAPI_start_counters - FAILED\n");
        exit(1);
    }

    matmul((double *)a, (double *)b, (double *)c, size, size, size);

    /* Read the counters */
    if (PAPI_read_counters(values, NUM_EVENTS) != PAPI_OK) {
        fprintf(stderr, "PAPI_read_counters - FAILED\n");
        exit(1);
    }

    printf("Total instructions: %lld\n", values[0]);
    printf("Total cycles: %lld\n", values[1]);
    printf("Instr per cycle: %2.3f\n", (double)values[0] / (double) values[1]);
    printf("Branches mispredicted: %lld\n", values[2]);
    printf("L1 Cache misses: %lld\n", values[3]);

    /* Stop counting events */
    if (PAPI_stop_counters(values, NUM_EVENTS) != PAPI_OK) {
        fprintf(stderr, "PAPI_stoped_counters - FAILED\n");
        exit(1);
    }

    return 0;
}

在 Intel Q6600 上对此进行了测试，它最多支持 4 个性能事件。您的处理器可能支持或多或少。

Looks like PAPI has very clean API and works just fine on Ubuntu 11.04.
Once it's installed, following app will do what I wanted:

#include <stdio.h>
#include <stdlib.h>
#include <papi.h>

#define NUM_EVENTS 4

void matmul(const double *A, const double *B,
        double *C, int m, int n, int p)
{
    int i, j, k;
    for (i = 0; i < m; ++i)
        for (j = 0; j < p; ++j) {
            double sum = 0;
            for (k = 0; k < n; ++k)
                sum += A[i*n + k] * B[k*p + j];
            C[i*p + j] = sum;
        }
}

int main(int /* argc */, char ** /* argv[] */)
{
    const int size = 300;
    double a[size][size];
    double b[size][size];
    double c[size][size];

    int event[NUM_EVENTS] = {PAPI_TOT_INS, PAPI_TOT_CYC, PAPI_BR_MSP, PAPI_L1_DCM };
    long long values[NUM_EVENTS];

    /* Start counting events */
    if (PAPI_start_counters(event, NUM_EVENTS) != PAPI_OK) {
        fprintf(stderr, "PAPI_start_counters - FAILED\n");
        exit(1);
    }

    matmul((double *)a, (double *)b, (double *)c, size, size, size);

    /* Read the counters */
    if (PAPI_read_counters(values, NUM_EVENTS) != PAPI_OK) {
        fprintf(stderr, "PAPI_read_counters - FAILED\n");
        exit(1);
    }

    printf("Total instructions: %lld\n", values[0]);
    printf("Total cycles: %lld\n", values[1]);
    printf("Instr per cycle: %2.3f\n", (double)values[0] / (double) values[1]);
    printf("Branches mispredicted: %lld\n", values[2]);
    printf("L1 Cache misses: %lld\n", values[3]);

    /* Stop counting events */
    if (PAPI_stop_counters(values, NUM_EVENTS) != PAPI_OK) {
        fprintf(stderr, "PAPI_stoped_counters - FAILED\n");
        exit(1);
    }

    return 0;
}

Tested this on Intel Q6600, it supports up to 4 performance events. Your processor may support more or less.

回复收藏 0 原文